@inproceedings{graca-etal-2008-building,
title = "Building a Golden Collection of Parallel Multi-Language Word Alignment",
author = "Gra{\c{c}}a, Jo{\~a}o and
Pardal, Joana Paulo and
Coheur, Lu{\'\i}sa and
Caseiro, Diamantino",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/250_paper.pdf",
abstract = "This paper reports an experience on producing manual word alignments over six different language pairs (all combinations between Portuguese, English, French and Spanish) (Gra{\c{c}}a et al., 2008). Word alignment of each language pair is made over the first 100 sentences of the common test set from the Europarl corpora (Koehn, 2005), corresponding to 600 new annotated sentences. This collection is publicly available at http://www.l2f.inesc- id.pt/resources/translation/. It contains, to our knowledge, the first word alignment gold set for the Portuguese language, with three other languages. Besides, it is to our knowledge, the first multi-language manual word aligned parallel corpus, where the same sentences are annotated for each language pair. We started by using the guidelines presented at (Mari{\~n}o, 2005) and performed several refinements: some due to under-specifications on the original guidelines, others because of disagreement on some choices. This lead to the development of an extensive new set of guidelines for multi-lingual word alignment annotation that, we believe, makes the alignment process less ambiguous. We evaluate the inter-annotator agreement obtaining an average of 91.6{\%} agreement between the different language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="graca-etal-2008-building">
<titleInfo>
<title>Building a Golden Collection of Parallel Multi-Language Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Graça</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joana</namePart>
<namePart type="given">Paulo</namePart>
<namePart type="family">Pardal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luísa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diamantino</namePart>
<namePart type="family">Caseiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports an experience on producing manual word alignments over six different language pairs (all combinations between Portuguese, English, French and Spanish) (Graça et al., 2008). Word alignment of each language pair is made over the first 100 sentences of the common test set from the Europarl corpora (Koehn, 2005), corresponding to 600 new annotated sentences. This collection is publicly available at http://www.l2f.inesc- id.pt/resources/translation/. It contains, to our knowledge, the first word alignment gold set for the Portuguese language, with three other languages. Besides, it is to our knowledge, the first multi-language manual word aligned parallel corpus, where the same sentences are annotated for each language pair. We started by using the guidelines presented at (Mariño, 2005) and performed several refinements: some due to under-specifications on the original guidelines, others because of disagreement on some choices. This lead to the development of an extensive new set of guidelines for multi-lingual word alignment annotation that, we believe, makes the alignment process less ambiguous. We evaluate the inter-annotator agreement obtaining an average of 91.6% agreement between the different language pairs.</abstract>
<identifier type="citekey">graca-etal-2008-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/250_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Golden Collection of Parallel Multi-Language Word Alignment
%A Graça, João
%A Pardal, Joana Paulo
%A Coheur, Luísa
%A Caseiro, Diamantino
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F graca-etal-2008-building
%X This paper reports an experience on producing manual word alignments over six different language pairs (all combinations between Portuguese, English, French and Spanish) (Graça et al., 2008). Word alignment of each language pair is made over the first 100 sentences of the common test set from the Europarl corpora (Koehn, 2005), corresponding to 600 new annotated sentences. This collection is publicly available at http://www.l2f.inesc- id.pt/resources/translation/. It contains, to our knowledge, the first word alignment gold set for the Portuguese language, with three other languages. Besides, it is to our knowledge, the first multi-language manual word aligned parallel corpus, where the same sentences are annotated for each language pair. We started by using the guidelines presented at (Mariño, 2005) and performed several refinements: some due to under-specifications on the original guidelines, others because of disagreement on some choices. This lead to the development of an extensive new set of guidelines for multi-lingual word alignment annotation that, we believe, makes the alignment process less ambiguous. We evaluate the inter-annotator agreement obtaining an average of 91.6% agreement between the different language pairs.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/250_paper.pdf
Markdown (Informal)
[Building a Golden Collection of Parallel Multi-Language Word Alignment](http://www.lrec-conf.org/proceedings/lrec2008/pdf/250_paper.pdf) (Graça et al., LREC 2008)
ACL